ProofTrail MCP Skill
Teach the agent how to install, connect, and use ProofTrail’s governed MCP
surface as a browser-evidence and recovery layer.
Use this skill when
- the host can attach a local stdio MCP server from a repo checkout
- the user needs governed browser-evidence reads before broad automation
- the operator wants a truthful packet that separates current repo-native MCP
from future package or Docker publication
What this package teaches
- how to launch ProofTrail’s current repo-native MCP server
- how to choose the safest ProofTrail tool families first
- how to move from catalog and read tools into governed run or proof tools
- how to talk about future npm, Docker, or registry surfaces without
overclaiming publication
What ProofTrail is
ProofTrail is an evidence-first browser automation and recovery layer.
It helps AI agents and human operators:
- run browser workflows through a governed path
- inspect retained evidence after each run
- recover from failures without pretending the browser layer is a generic bot
Start here
- Read references/INSTALL.md
- Load the right host config from:
- Skim the tool surface in references/CAPABILITIES.md
- Run the first-success path in references/DEMO.md
Safe-first workflow
uiq_catalog
uiq_read
uiq_quality_read
uiq_proof
- only then widen into:
uiq_run
uiq_run_and_report
uiq_api_workflow
uiq_api_automation
Suggested first prompt
Use ProofTrail as a governed browser-evidence layer. Start with uiq_catalog
to confirm the MCP surface is attached. Then use uiq_read or
uiq_quality_read to inspect one existing run or failure surface. If a real run
is already present, follow with uiq_proof or uiq_run_and_report to show the
retained evidence and summarize the most important next action.
Current / usable today
Current install path:
- clone the ProofTrail repo
- run
pnpm install
- point your MCP client at the repo-local stdio command
- start the MCP bridge with
pnpm mcp:start
Protocol and auth truth:
- auth =
local-with-optional-backend-token
Live public discovery lane
- the ClawHub page at
https://clawhub.ai/skills/prooftrail-mcp is live
- that page is a public discovery page for this repo-owned skill packet
- it does not turn ProofTrail into a hosted MCP endpoint, official plugin,
or generic cross-host skill-registry publication
Repo-owned packet and review lanes
- this skill folder is the repo-owned install packet
- Goose now has a live review receipt at
https://github.com/block/agent-skills/pull/26
- agent-skill.co now has a live review receipt at
https://github.com/heilcheng/awesome-agent-skills/pull/182
- awesome-opencode now has a live project-entry review receipt at
https://github.com/awesome-opencode/awesome-opencode/pull/275
- the OpenHands/extensions submission is now a closed historical receipt, not
a current review lane
- no generic cross-host skill-registry publication is evidenced today
Publish-ready but not yet published
The following install surfaces are planned and not yet published:
- npm package:
@prooftrail/mcp-server
- Docker image:
ghcr.io/xiaojiou176-open/prooftrail-mcp-server:0.1.1
Do not describe either surface as live until the package or image is actually
published.
Success checks
- the host attaches the repo-native MCP server successfully
- the agent cites a real run, artifact, or proof bundle instead of describing a
generic browser story
- the answer stays grounded in evidence instead of free-writing from memory
Boundaries
- this packet is not an official plugin
- ProofTrail is not a hosted service
- ProofTrail is not a hosted SaaS service
- ProofTrail is not a hosted MCP endpoint
- this packet may appear as a live ClawHub skill page, but that does not turn
ProofTrail into an official plugin or hosted MCP endpoint
- this packet does not claim a live OpenHands/extensions listing
- this packet does not claim a live Goose, agent-skill.co, or awesome-opencode
listing without fresh read-back
- future npm or Docker shapes are publish-ready but not yet published
Local references